Abstract
Advances in bio-technologies enable the generation of genomic data from various platforms. The accumulated omic data provides an opportunity to exploit the underlying mechanisms of cancers, and imposes a great challenge on designing algorithms for the integration of heterogeneous genomic data. Clustering of gene interaction networks is a promising approach for revealing the structure and functions of genes. However, current algorithms are criticized for either ignoring the attributes of genes or their high complexity. To overcome these problems, we propose a novel algorithm for cancer attributed networks (called jGENMF-AN), wherein graph representation and nonnegative matrix factorization are integrated. Specifically, graph representation learning is employed to obtain the low-dimensional features by preserving topology of the attributed networks, thereby reducing the complexity of the algorithm. To address heterogeneity of the topological features and attributes of genes, nonnegative matrix factorization for graph embedding and dimension reduction for the attribute matrix are jointly learned with a smoothness strategy. The experimental results indicate that jGENMF-AN is more accurate than state-of-the-art methods in the social and cancer attributed networks. The proposed model and algorithm provide an effective strategy for the integrative analysis of genomic data.
Highlights
Genes are the basic units of organisms and tissues, which work together to execute the critical biological processes in order to maintain the operations of biological systems [1]
To further validate the performance of jGENMFAN, we investigate whether the proposed algorithm can identify biological meaningful clusters from cancer attributed networks
These results indicate that the proposed algorithm can extract clusters from attributed networks that are more enriched by the known functions, implying that jGENMF-AN is applicable to attributed networks with strong backgrounds
Summary
Genes are the basic units of organisms and tissues, which work together to execute the critical biological processes in order to maintain the operations of biological systems [1]. Evidences demonstrate that the hyer-graph regularization is promising for network analysis because it can exploit the high-order structure of networks [17], [18] These algorithms can be broadly classified into two categories, i.e., topological optimization- and matrix decomposition-based methods. The topological and attribute features are jointly learned by incorporating these two tasks into an objective function In this case, the graph clustering of attributed networks is transformed into a constrained optimization problem, where the joint learning alleviates the conflict of heterogeneous features at a large content. - The experimental results demonstrate that the proposed algorithm outperforms state-of-the-art methods in terms of accuracy, which provides an efficient strategy to analyze the attributed networks.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
